© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116559
    Prev
    Next
    INDEX
    Explanations

    helicopter rotor blades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paradigma
    -0.81
    crafting
    -0.79
     condominio
    -0.77
     OAK
    -0.75
     leopardo
    -0.75
     palme
    -0.75
     persil
    -0.73
     respeito
    -0.71
     perifer
    -0.71
     equilibrio
    -0.71
    POSITIVE LOGITS
     Pasteur
    0.78
    規制
    0.77
     taux
    0.77
     XX
    0.76
     Carbon
    0.75
     gain
    0.73
     Khal
    0.72
    anover
    0.72
     antis
    0.71
     wysy
    0.71
    Activations Density 0.017%

    No Known Activations